commit f5a1f7d5ea395fcb2dd912ffab34461ec838ed46 Author: ModelHub XC Date: Sun Aug 30 04:00:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: xDAN-AI/xDAN-L1-SOLAR-RL-v1 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..e53de33 --- /dev/null +++ b/README.md @@ -0,0 +1,23 @@ +--- +license: cc-by-4.0 +datasets: +- Open-Orca/OpenOrca +- OpenAssistant/oasst2 +tags: +- xDAN-AI +--- + +
+ +
+ +This is a finetune-RL model based on SOLAR10.7B. + + +Disclaimer +We employ rigorous data compliance validation algorithms throughout the training of our language model to ensure the highest level of compliance. However, due to the intricate nature of data and the wide range of potential usage scenarios for the model, we cannot guarantee that it will consistently produce accurate and sensible outputs. Users should be aware of the possibility of the model generating problematic results. Our organization disclaims any responsibility for risks or issues arising from misuse, improper guidance, unlawful usage, misinformation, or subsequent concerns regarding data security. + +About xDAN-AI +xDAN-AI represents the forefront of Silicon-Based Life Factory technology. For comprehensive information and deeper insights into our cutting-edge technology and offerings, please visit our website: https://www.xdan.ai. + \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..27ee85f --- /dev/null +++ b/config.json @@ -0,0 +1,29 @@ +{ + "_name_or_path": "upstage/SOLAR-10.7B-Instruct-v1.0", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 4096, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 48, + "num_key_value_heads": 8, + "pad_token_id": 2, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.36.2", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..11220c6 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,8 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "pad_token_id": 2, + "transformers_version": "4.36.2", + "use_cache": false +} diff --git a/model-00001-of-00049.safetensors b/model-00001-of-00049.safetensors new file mode 100644 index 0000000..6bc75b8 --- /dev/null +++ b/model-00001-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06a2fae8208c2c3cb986b04a778c67fa8ffe2865ff7524cb567fbd411b22b299 +size 926941888 diff --git a/model-00002-of-00049.safetensors b/model-00002-of-00049.safetensors new file mode 100644 index 0000000..7014f9b --- /dev/null +++ b/model-00002-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf9e7bd27afa906353c7f6afc2639238a1a4b825057201361f5eb9c92dfc6604 +size 872449040 diff --git a/model-00003-of-00049.safetensors b/model-00003-of-00049.safetensors new file mode 100644 index 0000000..06a000d --- /dev/null +++ b/model-00003-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e76903a669a89e9bca388002f5b300d002cc3ffad519f6c66f598a5fe8e63ec +size 872449040 diff --git a/model-00004-of-00049.safetensors b/model-00004-of-00049.safetensors new file mode 100644 index 0000000..c9ed8b4 --- /dev/null +++ b/model-00004-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51a63b6c8d9a4bc4b052251dac42916c117ef0e80e231a924ab7bf8d212021fc +size 872449040 diff --git a/model-00005-of-00049.safetensors b/model-00005-of-00049.safetensors new file mode 100644 index 0000000..a2e3f5b --- /dev/null +++ b/model-00005-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94e55d9fca0dff9a364a588f47b1043c8eaed344baa032e4d88be9689ed3837a +size 872449040 diff --git a/model-00006-of-00049.safetensors b/model-00006-of-00049.safetensors new file mode 100644 index 0000000..026810f --- /dev/null +++ b/model-00006-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af4ab32479316733af2d9251780898deee9f86436d1692a808064834edaa412f +size 872449040 diff --git a/model-00007-of-00049.safetensors b/model-00007-of-00049.safetensors new file mode 100644 index 0000000..b75a720 --- /dev/null +++ b/model-00007-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fb07430c89fde030f6b47a5a7ac634d9baee9aa01e3cebfbdcd0adffa0c0e59 +size 872449040 diff --git a/model-00008-of-00049.safetensors b/model-00008-of-00049.safetensors new file mode 100644 index 0000000..df258cf --- /dev/null +++ b/model-00008-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ab48378e0dc2602f9cbaa81e3fabcf9a272051970626fd5e982f4f1493883c1 +size 872449040 diff --git a/model-00009-of-00049.safetensors b/model-00009-of-00049.safetensors new file mode 100644 index 0000000..d9769a8 --- /dev/null +++ b/model-00009-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a02736787406ff2cbadb9e11915cd467ef612b3cd7448d86621eeb144dd1adc +size 872449040 diff --git a/model-00010-of-00049.safetensors b/model-00010-of-00049.safetensors new file mode 100644 index 0000000..a36a87f --- /dev/null +++ b/model-00010-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29c3b92076d5e0d5e1eef82f45678c69e59ab588aba32251129f9508fece2d25 +size 872449040 diff --git a/model-00011-of-00049.safetensors b/model-00011-of-00049.safetensors new file mode 100644 index 0000000..8b893ca --- /dev/null +++ b/model-00011-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7cf9fa9be23041f458efe99c50e77ae10fa0329752a4d6fce6cd57ec691b7d6 +size 872449056 diff --git a/model-00012-of-00049.safetensors b/model-00012-of-00049.safetensors new file mode 100644 index 0000000..5ab84fc --- /dev/null +++ b/model-00012-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:441566cdf789e5d6fe4b0734d09a3f8d9b6470ab92d91f20a230df2814717788 +size 872449048 diff --git a/model-00013-of-00049.safetensors b/model-00013-of-00049.safetensors new file mode 100644 index 0000000..8d663af --- /dev/null +++ b/model-00013-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd26917531e608b9adf0c1bf5bd6328acfe11bf3164b6dc0ec7f21f4da1bba06 +size 872449048 diff --git a/model-00014-of-00049.safetensors b/model-00014-of-00049.safetensors new file mode 100644 index 0000000..3248304 --- /dev/null +++ b/model-00014-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cdfc74d206da210d418671d0aaf719f37913bc4334637b28a366509993b69f2 +size 872449048 diff --git a/model-00015-of-00049.safetensors b/model-00015-of-00049.safetensors new file mode 100644 index 0000000..5a3b614 --- /dev/null +++ b/model-00015-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b89ac7850a943075606060de3df598eb06266e5f199f9a973f0ab9c0cc6920a0 +size 872449048 diff --git a/model-00016-of-00049.safetensors b/model-00016-of-00049.safetensors new file mode 100644 index 0000000..9abd810 --- /dev/null +++ b/model-00016-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6d23de0a16566f86ba489be28b264f048b32a8363d0cbf7bd1b1581d7e31ff9 +size 872449048 diff --git a/model-00017-of-00049.safetensors b/model-00017-of-00049.safetensors new file mode 100644 index 0000000..1000c4b --- /dev/null +++ b/model-00017-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3fbfdeb00b4b60273b37e8434c6e1d5f4f8ba51f91ce38488d5c8d971de1656 +size 872449048 diff --git a/model-00018-of-00049.safetensors b/model-00018-of-00049.safetensors new file mode 100644 index 0000000..c3bd764 --- /dev/null +++ b/model-00018-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9f4e95cf7a52526dd7c9c34ca9a85047487f8ab9307e3e1db5c30b4d855d379 +size 872449048 diff --git a/model-00019-of-00049.safetensors b/model-00019-of-00049.safetensors new file mode 100644 index 0000000..ba8483d --- /dev/null +++ b/model-00019-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c9ac145c9a6752a28e4ed5a113b324884a8efa2c5cbc2e93994e601de820a83 +size 872449048 diff --git a/model-00020-of-00049.safetensors b/model-00020-of-00049.safetensors new file mode 100644 index 0000000..dfe7039 --- /dev/null +++ b/model-00020-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:278bbe12b760c75c087ba574b425d37047e95a88b0111f104a84c5bc687ed57c +size 872449048 diff --git a/model-00021-of-00049.safetensors b/model-00021-of-00049.safetensors new file mode 100644 index 0000000..84e5be4 --- /dev/null +++ b/model-00021-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b9d4447682b8b9e46617102b8797dbc682f7fb9d2311c50397bf4576eee4e6b +size 872449048 diff --git a/model-00022-of-00049.safetensors b/model-00022-of-00049.safetensors new file mode 100644 index 0000000..bbc168b --- /dev/null +++ b/model-00022-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b59d098a0ed3b02044de71672c9c9742f1112037994e88fda3727499c9343f2c +size 872449048 diff --git a/model-00023-of-00049.safetensors b/model-00023-of-00049.safetensors new file mode 100644 index 0000000..9a6c54f --- /dev/null +++ b/model-00023-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a68aaeb0daf8db9e1abf46c9f69073d7ba3dec663ac7b20d04fbda63d56728e +size 872449048 diff --git a/model-00024-of-00049.safetensors b/model-00024-of-00049.safetensors new file mode 100644 index 0000000..baa05d8 --- /dev/null +++ b/model-00024-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9df273168035016992c333454ff4f73ba04b3c54f38c14993cc1f281ccf00ad4 +size 872449048 diff --git a/model-00025-of-00049.safetensors b/model-00025-of-00049.safetensors new file mode 100644 index 0000000..8d2742e --- /dev/null +++ b/model-00025-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a6e3a3fe50dd59ffcb43fe3c263fbec0d8c8bc40b43b03a3c5c80173fdca9d4 +size 872449048 diff --git a/model-00026-of-00049.safetensors b/model-00026-of-00049.safetensors new file mode 100644 index 0000000..8c5d818 --- /dev/null +++ b/model-00026-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b82b1f9a03c844452b20b8010d243225505c8b2fd29618000c3e4335871e504 +size 872449048 diff --git a/model-00027-of-00049.safetensors b/model-00027-of-00049.safetensors new file mode 100644 index 0000000..fe1eb16 --- /dev/null +++ b/model-00027-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d879727fcc3d123fa34d8ba6d1d1108490404e72447a710f56f005b718e4f31 +size 872449048 diff --git a/model-00028-of-00049.safetensors b/model-00028-of-00049.safetensors new file mode 100644 index 0000000..ed4d43a --- /dev/null +++ b/model-00028-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d66b638dcc5c41050a53b13dc1d2f543b35a747560a65d931e86b095c269fb6 +size 872449048 diff --git a/model-00029-of-00049.safetensors b/model-00029-of-00049.safetensors new file mode 100644 index 0000000..3c1aa94 --- /dev/null +++ b/model-00029-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c002668d74155acc3294aeaa1d2f2fd433f59a4ec26807e21b82db4c8542621d +size 872449048 diff --git a/model-00030-of-00049.safetensors b/model-00030-of-00049.safetensors new file mode 100644 index 0000000..6e1a072 --- /dev/null +++ b/model-00030-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6eb27a67209c6504a4d3d62d945d45a46a54c0f620b7057097fd7ca346b5cdd6 +size 872449048 diff --git a/model-00031-of-00049.safetensors b/model-00031-of-00049.safetensors new file mode 100644 index 0000000..8cbcc0f --- /dev/null +++ b/model-00031-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30744681a7e1c04cfb6fafe69b89b324a8576d8f5ea29c25b5fe111cba94bbdd +size 872449048 diff --git a/model-00032-of-00049.safetensors b/model-00032-of-00049.safetensors new file mode 100644 index 0000000..4433f04 --- /dev/null +++ b/model-00032-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b679965338ff97f14c1026c4d9134e56c0df994e07bb2b33aa07b4115444882f +size 872449048 diff --git a/model-00033-of-00049.safetensors b/model-00033-of-00049.safetensors new file mode 100644 index 0000000..d33c5b5 --- /dev/null +++ b/model-00033-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae25f1a8a695c6de647cdfc9feacafe23de822b0047fa73b0cf2e7f60acbe511 +size 872449048 diff --git a/model-00034-of-00049.safetensors b/model-00034-of-00049.safetensors new file mode 100644 index 0000000..5b4c1aa --- /dev/null +++ b/model-00034-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa60b5ae1c0807e4386c68fcea460514601455c5ddad460e380787167d3f989f +size 872449048 diff --git a/model-00035-of-00049.safetensors b/model-00035-of-00049.safetensors new file mode 100644 index 0000000..b7285f4 --- /dev/null +++ b/model-00035-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:718180ecee12b9cde44f5a3884e31f9042b954fa1e01bc1a0c029c6ff4275998 +size 872449048 diff --git a/model-00036-of-00049.safetensors b/model-00036-of-00049.safetensors new file mode 100644 index 0000000..398e7dc --- /dev/null +++ b/model-00036-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03e336e7091f7ed8c7f17206e44b84b8f3fdb3a075a15a6726da3c4c7e029654 +size 872449048 diff --git a/model-00037-of-00049.safetensors b/model-00037-of-00049.safetensors new file mode 100644 index 0000000..e823755 --- /dev/null +++ b/model-00037-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2a45dd76afe34ec69b291e4bbc5d373750ebc24f2b28eb424ae30b36c7fa6e4 +size 872449048 diff --git a/model-00038-of-00049.safetensors b/model-00038-of-00049.safetensors new file mode 100644 index 0000000..cd38603 --- /dev/null +++ b/model-00038-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc08b494ec4662a2918eba1b6cdff408e6b63c069b8c87a5dbead67e6b7f8851 +size 872449048 diff --git a/model-00039-of-00049.safetensors b/model-00039-of-00049.safetensors new file mode 100644 index 0000000..f08e4e9 --- /dev/null +++ b/model-00039-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba78c4ac11817063ce75f5ae587f9857615a80288eba1bfe25531f9d201592e3 +size 872449048 diff --git a/model-00040-of-00049.safetensors b/model-00040-of-00049.safetensors new file mode 100644 index 0000000..9666cc5 --- /dev/null +++ b/model-00040-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c0453e07473ba08dced5c2bb8fbbf6da75939b09110f190d73878703ab37d3b +size 872449048 diff --git a/model-00041-of-00049.safetensors b/model-00041-of-00049.safetensors new file mode 100644 index 0000000..1c295fa --- /dev/null +++ b/model-00041-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dddb7e3fa3533cb21c6875be9e6480ef282fedf31ae79650041739c7f25196a +size 872449048 diff --git a/model-00042-of-00049.safetensors b/model-00042-of-00049.safetensors new file mode 100644 index 0000000..3833a6c --- /dev/null +++ b/model-00042-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e62e42a3aba791eb84ba33ca0f9d6c2a1db70036136c0300ae96b9775fe0864 +size 872449048 diff --git a/model-00043-of-00049.safetensors b/model-00043-of-00049.safetensors new file mode 100644 index 0000000..89c87fe --- /dev/null +++ b/model-00043-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91dbb42d586aa58e36fbffe9ad33ee112c3f0dee1ad7cbffc299286b4e28bb89 +size 872449048 diff --git a/model-00044-of-00049.safetensors b/model-00044-of-00049.safetensors new file mode 100644 index 0000000..1a565ce --- /dev/null +++ b/model-00044-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:716954e469216ed37b8d17c8b613a3cab072056ca7b7d8c14006e3813a737865 +size 872449048 diff --git a/model-00045-of-00049.safetensors b/model-00045-of-00049.safetensors new file mode 100644 index 0000000..6aa6bc4 --- /dev/null +++ b/model-00045-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fd5a2488ff3ea572c64f86eb33796a1ad57e479be96fa7672a155394b153013 +size 872449048 diff --git a/model-00046-of-00049.safetensors b/model-00046-of-00049.safetensors new file mode 100644 index 0000000..92225e3 --- /dev/null +++ b/model-00046-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ac513287ab28b2ba8cf249bb79ef9529cab6aa5d9ce59bde51826c79b66fdbf +size 872449048 diff --git a/model-00047-of-00049.safetensors b/model-00047-of-00049.safetensors new file mode 100644 index 0000000..09f1f72 --- /dev/null +++ b/model-00047-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bebba2d8e24ad287dadc66b9f54dbcb102ce77b0a1aae79d2335a91e8ed23555 +size 872449048 diff --git a/model-00048-of-00049.safetensors b/model-00048-of-00049.safetensors new file mode 100644 index 0000000..d8f084d --- /dev/null +++ b/model-00048-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39d16c7440ba2012042703afbef3b03bc4704b7dad3b45e55b1678b26f27ed73 +size 872449048 diff --git a/model-00049-of-00049.safetensors b/model-00049-of-00049.safetensors new file mode 100644 index 0000000..0da2522 --- /dev/null +++ b/model-00049-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01137edf0e7f2c3e2d17f8b7c634c8232d2302a163100c5cb43212fb464fe752 +size 994099864 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..4af87f2 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,442 @@ +{ + "metadata": { + "total_size": 42926096384 + }, + "weight_map": { + "lm_head.weight": "model-00049-of-00049.safetensors", + "model.embed_tokens.weight": "model-00001-of-00049.safetensors", + "model.layers.0.input_layernorm.weight": "model-00002-of-00049.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00049.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.input_layernorm.weight": "model-00003-of-00049.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00049.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.10.input_layernorm.weight": "model-00012-of-00049.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00012-of-00049.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.input_layernorm.weight": "model-00013-of-00049.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00013-of-00049.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.input_layernorm.weight": "model-00014-of-00049.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00014-of-00049.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.input_layernorm.weight": "model-00015-of-00049.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00015-of-00049.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.input_layernorm.weight": "model-00016-of-00049.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00016-of-00049.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.input_layernorm.weight": "model-00017-of-00049.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00017-of-00049.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.input_layernorm.weight": "model-00018-of-00049.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00018-of-00049.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.input_layernorm.weight": "model-00019-of-00049.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00019-of-00049.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.input_layernorm.weight": "model-00020-of-00049.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00020-of-00049.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.input_layernorm.weight": "model-00021-of-00049.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00021-of-00049.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.2.input_layernorm.weight": "model-00004-of-00049.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00049.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.20.input_layernorm.weight": "model-00022-of-00049.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00022-of-00049.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.input_layernorm.weight": "model-00023-of-00049.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00023-of-00049.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.input_layernorm.weight": "model-00024-of-00049.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00024-of-00049.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.input_layernorm.weight": "model-00025-of-00049.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00025-of-00049.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.input_layernorm.weight": "model-00026-of-00049.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00026-of-00049.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.input_layernorm.weight": "model-00027-of-00049.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00027-of-00049.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.input_layernorm.weight": "model-00028-of-00049.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00028-of-00049.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.input_layernorm.weight": "model-00029-of-00049.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00029-of-00049.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.input_layernorm.weight": "model-00030-of-00049.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00030-of-00049.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.input_layernorm.weight": "model-00031-of-00049.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00031-of-00049.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.3.input_layernorm.weight": "model-00005-of-00049.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00049.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.30.input_layernorm.weight": "model-00032-of-00049.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00032-of-00049.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.input_layernorm.weight": "model-00033-of-00049.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00033-of-00049.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.input_layernorm.weight": "model-00034-of-00049.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00034-of-00049.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.input_layernorm.weight": "model-00035-of-00049.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00035-of-00049.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.input_layernorm.weight": "model-00036-of-00049.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00036-of-00049.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.input_layernorm.weight": "model-00037-of-00049.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00037-of-00049.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.input_layernorm.weight": "model-00038-of-00049.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00038-of-00049.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.input_layernorm.weight": "model-00039-of-00049.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00039-of-00049.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.input_layernorm.weight": "model-00040-of-00049.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00040-of-00049.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.input_layernorm.weight": "model-00041-of-00049.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00041-of-00049.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.4.input_layernorm.weight": "model-00006-of-00049.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00049.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.40.input_layernorm.weight": "model-00042-of-00049.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00042-of-00049.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.input_layernorm.weight": "model-00043-of-00049.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00043-of-00049.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.input_layernorm.weight": "model-00044-of-00049.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00044-of-00049.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.input_layernorm.weight": "model-00045-of-00049.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00045-of-00049.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.input_layernorm.weight": "model-00046-of-00049.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00046-of-00049.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.input_layernorm.weight": "model-00047-of-00049.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00047-of-00049.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.input_layernorm.weight": "model-00048-of-00049.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00048-of-00049.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.input_layernorm.weight": "model-00049-of-00049.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00049-of-00049.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.5.input_layernorm.weight": "model-00007-of-00049.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00049.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.input_layernorm.weight": "model-00008-of-00049.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00008-of-00049.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.input_layernorm.weight": "model-00009-of-00049.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00049.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.input_layernorm.weight": "model-00010-of-00049.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00049.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.input_layernorm.weight": "model-00011-of-00049.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00011-of-00049.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00049.safetensors", + "model.norm.weight": "model-00049-of-00049.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..492d4b2 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,30 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..8b443ef --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..8f1fd28 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,45 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{% if message['content']%}{{'### System:\n' + message['content']+'\n\n'}}{% endif %}{% elif message['role'] == 'user' %}{{'### User:\n' + message['content']+'\n\n'}}{% elif message['role'] == 'assistant' %}{{'### Assistant:\n' + message['content']}}{% endif %}{% if loop.last and add_generation_prompt %}{{ '### Assistant:\n' }}{% endif %}{% endfor %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "padding_side": "left", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "split_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +}